Radar Reference Mapping for Cost-Effective Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle localization methods for autonomous vehicles require expensive sensors and navigation systems to achieve sub-meter accuracy, which are unreliable in less-than-ideal lighting and weather conditions, and are not cost-effective for consumer vehicles.
Innovation Solution
The use of radar detection-based methods, including building and updating a radar reference map, to accurately localize vehicles using inexpensive radar sensors and lower-quality navigation systems, by processing radar data to identify stationary objects and determine vehicle pose.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive sensors and navigation systems (cameras, LiDAR, high-quality GNSS) are used to achieve sub-meter localization accuracy, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces expensive, complex sensors (cameras, LiDAR, high-quality GNSS) with inexpensive radar sensors and lower-quality navigation systems. The system achieves acceptable localization accuracy by using multiple iterations of radar data processing and map updates rather than relying on expensive single-shot measurements, effectively substituting cheap, iterative processing for expensive hardware
Solution Approach 2:
The patent substitutes optical and electromagnetic sensing systems (cameras, LiDAR) with radar-based detection systems. By using radar signal processing and normal distribution transformation grids, the system replaces complex optical/mechanical sensing with radio wave-based detection and computational geometry, achieving similar localization functionality with different, more cost-effective technology
2Measurement precision
If cameras and LiDAR are used for vehicle localization, then measurement precision is improved, but reliability deteriorates in less-than-ideal lighting and weather conditions
Solution Approach 1:
The patent changes the fundamental operating parameters of the sensing system from optical wavelengths (cameras, LiDAR) to radio wave frequencies (radar). Radar waves penetrate adverse weather conditions (rain, fog, snow) and operate independently of lighting conditions, maintaining reliable detection and localization accuracy where optical systems fail
3Measurement precision
If high-quality GNSS systems are integrated to achieve sub-meter localization accuracy, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent merges radar detections with navigation data from lower-quality navigation systems to achieve localization accuracy comparable to high-quality GNSS. By combining multiple data sources (radar detections, ego-trajectory information, landmark data) and processing them through iterative normal distribution transformation, the system achieves accurate localization without requiring expensive dedicated GNSS hardware
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate vehicle localization at a sub-meter level using cost-effective radar systems, even in adverse conditions, by generating and updating radar reference maps through multiple iterations, thereby overcoming the limitations of existing technologies.
Implementation Method 1
receiving, by at least one processor, radar detections from one or more radar sensors of the vehicle
Data Source
AI summary
This document describes methods and systems for vehicle localization based on radar detections. Radar localization starts with building a radar reference map. The radar reference map may be generated and updated using different techniques as described herein. Once a radar reference map is available, real-time localization may be achieved with inexpensive radar sensors and navigation systems. Using the techniques described in this document, the data from the radar sensors and the navigation systems may be processed to identify stationary localization objects, or landmarks, in the vicinity of the vehicle. Comparing the landmark data originating from the onboard sensors and systems of the vehicle with landmark data detailed in the radar reference map may generate an accurate pose of the vehicle in its environment. By using inexpensive radar systems and lower quality navigation systems, a highly accurate vehicle pose may be obtained in a cost-effective manner.